• The Journal of the Korea Contents Association
• /
• v.9 no.9
• /
• pp.80-89
• /
• 2009

A fast and efficient search algorithm to determine an optimal number of clusters in clustering algorithms is presented. The method is based on cluster validity index which is a measure for clustering optimality. As the clustering procedure progresses and reaches an optimal cluster configuration, the cluster validity index is expected to be minimized or maximized. In this Paper, a fast non-exhaustive search method for finding the optimal number of clusters is designed and shown to work well in clustering. The proposed algorithm is implemented with the k-mean++ algorithm as underlying clustering techniques using CB and PBM as a cluster validity index. Experimental results show that the proposed method provides the computation time efficiency without loss of accuracy on several artificial and real-life data sets.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.419-420
• /
• 2006

In the new video coding standard H.264/AVC, motion estimation (ME) is allowed to search multiple reference frames for improve the rate-distortion performance. The complexity of multi-frame motion estimation increases linearly with the number of used reference frame. However, the distortion gain given by each reference frame varies with the video sequence, and it is not efficient to search through all the candidate frames. In this paper, we propose a fast mult-frame selection method using all zero coefficient block (AZCB) prediction and sum of difference (SAD) of neighbor block. Simulation results show that the speed of the proposed algorithm is up to two times faster than exhaustive search of multiple reference frames with similar quality and bit-rate.

• The Korean Journal of Applied Statistics
• /
• v.14 no.2
• /
• pp.475-486
• /
• 2001

데이터마이닝 패키지에 구현된 분류나무 알고리즘 가운데 CART, CHAID, QUEST, C4.5에서 변수 선택법을 비교하였다. CART의 전체탐색법이 편의를 갖는다는 사실은 잘알려졌으며, 여기서는 상품화된 패키지들에서 이들 알고리즘의 편의와 선택력을 모의실험 연구를 통하여 비교하였다. 상용 패키지로는 CART, Enterprise Miner, AnswerTree, Clementine을 사용하였다. 본 논문의 제한된 모의실험 연구 결과에 의하면 C4.5와 CART는 모두 변수선택에서 심각한 편의를 갖고 있으며, CHAID와 QUEST는 비교적 안정된 결과를 보여주고 있었다.

• Structural Engineering and Mechanics
• /
• v.70 no.3
• /
• pp.367-380
• /
• 2019

The paper concerns topology and geometry optimization of statically determinate beams with arbitrary number of supports. The optimization problem is treated as a bi-criteria one, with the objectives of minimizing the absolute maximum bending moment and the maximum deflection for a uniform gravity load. The problem is formulated and solved using the Pareto optimality concept and the lexicographic ordering of the objectives. The non-dominated sorting genetic algorithm NSGA-II and the local search method are used for the optimization in the Pareto sense, whereas the genetic algorithm and the exhaustive search method for the lexicographic optimization. Trade-offs between objectives are examined and sets of Pareto-optimal solutions are provided for different topologies. Lexicographically optimal beams are found assuming that the maximum moment is a more important criterion. Exact formulas for locations and values of the maximum deflection are given for all lexicographically optimal beams of any topology and any number of supports. Topologies with lexicographically optimal geometries are classified into equivalence classes, and specific features of these classes are discussed. A qualitative principle of the division of topologies equivalent in terms of the maximum moment into topologies better and worse in terms of the maximum deflection is found.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.11C
• /
• pp.1098-1107
• /
• 2005

The emerging H.264/AVC video coding standard improves coding performance significantly by adopting many advanced techniques. This is achieved at the expense of great increasing encoder complexity. Specifically the intra prediction using RDO examines all possible combinations of coding modes, which depend on spatial directional correlation with adjacent blocks. For 4${\times}$4 luma blocks, there are 9 modes, and for 16${\times}$16 luma and 8${\times}$8 chroma blocks, there are 4 modes, respectively. Therefore the number of mode combinations for each macroblock is 592. This paper presents a method to reduce the RDO complexity using simple directional masks and neighboring modes. According to the proposed method, we reduce the number of mode combinations to 132 at the most. Experimental results show the proposed method reduces the encoding time up to $70\%$ with negligible loss of PSNR and bitrate increase compared to the H.264/AVC exhaustive search.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.25 no.10
• /
• pp.1062-1068
• /
• 2014

In this paper, a novel approach estimating target's rotation velocity(RV) is proposed for inverse synthetic aperture radar(ISAR) cross-range scaling(CRS). Scale invariant feature transform(SIFT) is applied to two sequently generated ISAR images for extracting non-fluctuating scatterers. Considering the fact that the distance between target's rotation center(RC) and SIFT features is same, we can set a criterion for estimating RV. Then, the criterion is optimized through the proposed method based on particle swarm optimization(PSO) combined with exhaustive search method. Simulation results show that the proposed algorithm can precisely estimate RV of a scenario based maneuvering target without RC information. With the use of the estimated RV, ISAR image can be correctly re-scaled along the cross-range direction.

• Journal of Korea Multimedia Society
• /
• v.18 no.11
• /
• pp.1289-1301
• /
• 2015

Pedestrian detection (PD) is an essential task in various applications and sliding window-based methods utilizing HOG (Histogram of Oriented Gradients) or HOG-like descriptors have been shown to be very effective for accurate PD. However, due to exhaustive search across images, PD methods based on sliding window usually require heavy computational time. In this paper, we propose a real-time PD method for embedded visual surveillance with fixed backgrounds. The proposed PD method employs HOG descriptors as many PD methods does, but utilizes selective search so that it can save processing time significantly. The proposed selective search is guided by restricting searching to candidate regions extracted from Adaptive Gaussian Mixture Model (AGMM)-based background subtraction technique. Moreover, approximate computation of HOG descriptor and implementation in fixed-point arithmetic mode contributes to reduction of processing time further. Possible accuracy degradation due to approximate computation is compensated by applying an appropriate one among three offline trained SVM classifiers according to sizes of candidate regions. The experimental results show that the proposed PD method significantly improves processing speed without noticeable accuracy degradation compared to the original HOG-based PD and HOG with cascade SVM so that it is a suitable real-time PD implementation for embedded surveillance systems.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.7C
• /
• pp.719-725
• /
• 2003

The content-based image retrieval system extracts features of color, shape and texture from raw images, and builds the database with those features in the indexing process. The search in the whole retrieval system is defined as a process which finds images that have large similarity to query image using the feature database. This paper proposes a new two-stage search method in the content-based image retrieval system. The method is that the features are condensed and stored by the property of Cauchy-Schwartz inequality in order to reduce the similarity computation time which takes a mostly response time from entering a query to getting retrieval results. By the extensive computer simulations, we have observed that the proposed two-stage search method successfully reduces the similarity computation time while maintaining the same retrieval relevance as the conventional exhaustive search method. We also have observed that the method is more effective as the number of images and dimensions of the feature space increase.

• 한국생물공학회:학술대회논문집
• /
• 2002.04a
• /
• pp.539-542
• /
• 2002

We propose new encoding method for numerical data in DNA using temperature gradient. To represent numerical values in DNA sequences, we introduce melting temperature. Since DNA strands representing smaller values have a lower Tm, they tend to denature with ease and also easily amplified by denaturation temperature gradient PCR. We also implement a local search molecular algorithm using temperature gradient, which is contrasted to conventional exhaustive search molecular algorithms. The proposed methods are verified by solving an instance of the travelling salesman problem. We could effectively amplify the correct solutions and the use of temperature gradient made the detection of solutions easier.

• ETRI Journal
• /
• v.39 no.3
• /
• pp.364-372
• /
• 2017

For the reliability of controllers in a software defined network (SDN), a dynamic and self-learning schedule method (DSL) is proposed. This method is original and easy to deploy, and optimizes the combination of multiple controllers. First, we summarize multiple controllers' combinations and schedule problems in an SDN and analyze its reliability. Then, we introduce the architecture of the schedule method and evaluate multi-controller reliability, the DSL method, and its optimized solution. By continually and statistically learning the information about controller reliability, this method treats it as a metric to schedule controllers. Finally, we compare and test the method using a given testing scenario based on an SDN network simulator. The experiment results show that the DSL method can significantly improve the total reliability of an SDN compared with a random schedule, and the proposed optimization algorithm has higher efficiency than an exhaustive search.